submission_id: cgato-l3-thespice-8b-dp_3142_v13
developer_uid: c.gato
status: inactive
model_repo: cgato/L3-TheSpice-8b-DPO-v3.2-e13.2
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.85, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 200, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', 'You:'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|im_start|>system\n{bot_name}'s Persona: {memory}\n", 'prompt_template': '***\n{prompt}\n***<|im_end|>\n', 'bot_template': '<|im_start|>{bot_name}\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>{bot_name}\n{bot_name}:', 'truncate_by_message': True}
reward_formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': True}
timestamp: 2024-06-01T09:36:01+00:00
model_name: cgato-l3-thespice-8b-dp_3142_v13
model_eval_status: success
model_group: cgato/L3-TheSpice-8b-DPO
num_battles: 7286
num_wins: 4068
celo_rating: 1214.36
safety_score: 0.92
propriety_score: 0.75
propriety_total_count: 8.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030277632.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: cgato-l3-thespice-8b-dp_3142_v13
ineligible_reason: propriety_total_count < 5000
language_model: cgato/L3-TheSpice-8b-DPO-v3.2-e13.2
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-01
win_ratio: 0.5583310458413395
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-dp-3142-v13-mkmlizer
Waiting for job on cgato-l3-thespice-8b-dp-3142-v13-mkmlizer to finish
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: ║ ║
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: ║ Version: 0.8.14 ║
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: ║ https://mk1.ai ║
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: ║ ║
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: ║ ║
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: ║ ║
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_deprecation.py:131: FutureWarning: 'list_files_info' (from 'huggingface_hub.hf_api') is deprecated and will be removed from version '0.23'. Use `list_repo_tree` and `get_paths_info` instead.
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: Downloaded to shared memory in 17.585s
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 81.51it/s] Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 90.20it/s] Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 132.25it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: quantized model in 23.276s
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: Processed model cgato/L3-TheSpice-8b-DPO-v3.2-e13.2 in 43.421s
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-dp-3142-v13
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dp-3142-v13/config.json
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dp-3142-v13/special_tokens_map.json
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dp-3142-v13/tokenizer_config.json
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dp-3142-v13/tokenizer.json
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-dp-3142-v13/flywheel_model.0.safetensors
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:913: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:757: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:468: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: /opt/conda/lib/python3.10/site-packages/torch/_utils.py:831: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: Saving duration: 0.427s
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.338s
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-3142-v13_reward
cgato-l3-thespice-8b-dp-3142-v13-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-dp-3142-v13_reward/reward.tensors
Job cgato-l3-thespice-8b-dp-3142-v13-mkmlizer completed after 72.56s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-dp-3142-v13-mkmlizer
Pipeline stage MKMLizer completed in 76.02s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-dp-3142-v13
Waiting for inference service cgato-l3-thespice-8b-dp-3142-v13 to be ready
Inference service cgato-l3-thespice-8b-dp-3142-v13 ready after 40.1935350894928s
Pipeline stage ISVCDeployer completed in 47.26s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.215391159057617s
Received healthy response to inference request in 1.2934491634368896s
Received healthy response to inference request in 1.2976760864257812s
Received healthy response to inference request in 1.2868974208831787s
Received healthy response to inference request in 1.3021235466003418s
5 requests
0 failed requests
5th percentile: 1.288207769393921
10th percentile: 1.289518117904663
20th percentile: 1.2921388149261475
30th percentile: 1.294294548034668
40th percentile: 1.2959853172302247
50th percentile: 1.2976760864257812
60th percentile: 1.2994550704956054
70th percentile: 1.3012340545654297
80th percentile: 1.484777069091797
90th percentile: 1.850084114074707
95th percentile: 2.032737636566162
99th percentile: 2.178860454559326
mean time: 1.4791074752807618
Pipeline stage StressChecker completed in 8.03s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.04s
M-Eval Dataset for topic stay_in_character is loaded
cgato-l3-thespice-8b-dp_3142_v13 status is now deployed due to DeploymentManager action
cgato-l3-thespice-8b-dp_3142_v13 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics